{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31282249093055725, "min": 0.312415212392807, "max": 1.4210714101791382, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9309.59765625, "min": 9309.59765625, "max": 43109.62109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989893.0, "min": 29952.0, "max": 989893.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989893.0, "min": 29952.0, "max": 989893.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5829898118972778, "min": -0.08658622950315475, "max": 0.6059285998344421, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.0711669921875, "min": -20.953866958618164, "max": 170.8718719482422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.013254067860543728, "min": -0.06352107971906662, "max": 0.45471400022506714, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.684630870819092, "min": -17.087169647216797, "max": 109.13136291503906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06436205045403247, "min": 0.06377442098437569, "max": 0.0728279602271067, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9010687063564546, "min": 0.4941473512431264, "max": 1.0515144406475454, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01674903757382362, "min": 0.0005799516965754477, "max": 0.01679127351755077, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23448652603353068, "min": 0.008119323752056267, "max": 0.23507782924571075, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.274304718121429e-06, "min": 7.274304718121429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010184026605370001, "min": 0.00010184026605370001, "max": 0.0033812531729157, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024247357142857, "min": 0.1024247357142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339463, "min": 1.3691136000000002, "max": 2.5270843000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002522310978571429, "min": 0.0002522310978571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003531235370000001, "min": 0.003531235370000001, "max": 0.11273572157, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015900665894150734, "min": 0.015864307060837746, "max": 0.7090969085693359, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22260931134223938, "min": 0.22210028767585754, "max": 4.963678359985352, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 334.375, "min": 302.10752688172045, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29425.0, "min": 15984.0, "max": 32076.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6201477060941132, "min": -1.0000000521540642, "max": 1.6587225641774874, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 142.57299813628197, "min": -32.000001668930054, "max": 154.26119846850634, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6201477060941132, "min": -1.0000000521540642, "max": 1.6587225641774874, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 142.57299813628197, "min": -32.000001668930054, "max": 154.26119846850634, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05532462460641083, "min": 0.050817282933078994, "max": 14.738746363669634, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.868566965364153, "min": 4.726007312776346, "max": 235.81994181871414, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707591113", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707593691" }, "total": 2577.9088816309995, "count": 1, "self": 1.2495844069990198, "children": { "run_training.setup": { "total": 0.07326397400015594, "count": 1, "self": 0.07326397400015594 }, "TrainerController.start_learning": { "total": 2576.5860332500006, "count": 1, "self": 1.8555252440232834, "children": { "TrainerController._reset_env": { "total": 3.33563584500007, "count": 1, "self": 3.33563584500007 }, "TrainerController.advance": { "total": 2571.253055175977, "count": 63965, "self": 1.9412942889971418, "children": { "env_step": { "total": 1886.0530794999613, "count": 63965, "self": 1728.575071621056, "children": { "SubprocessEnvManager._take_step": { "total": 156.35503531497739, "count": 63965, "self": 5.63467198303033, "children": { "TorchPolicy.evaluate": { "total": 150.72036333194706, "count": 62574, "self": 150.72036333194706 } } }, "workers": { "total": 1.1229725639279877, "count": 63965, "self": 0.0, "children": { "worker_root": { "total": 2570.1263202629325, "count": 63965, "is_parallel": true, "self": 984.0523670609184, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005432106999933239, "count": 1, "is_parallel": true, "self": 0.003947838000385673, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014842689995475666, "count": 8, "is_parallel": true, "self": 0.0014842689995475666 } } }, "UnityEnvironment.step": { "total": 0.058826175999911356, "count": 1, "is_parallel": true, "self": 0.0006842020002295612, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006021109998073371, "count": 1, "is_parallel": true, "self": 0.0006021109998073371 }, "communicator.exchange": { "total": 0.05546333799998138, "count": 1, "is_parallel": true, "self": 0.05546333799998138 }, "steps_from_proto": { "total": 0.0020765249998930813, "count": 1, "is_parallel": true, "self": 0.00041314900045108516, "children": { "_process_rank_one_or_two_observation": { "total": 0.001663375999441996, "count": 8, "is_parallel": true, "self": 0.001663375999441996 } } } } } } }, "UnityEnvironment.step": { "total": 1586.073953202014, "count": 63964, "is_parallel": true, "self": 40.04072037908395, "children": { "UnityEnvironment._generate_step_input": { "total": 28.5910124509453, "count": 63964, "is_parallel": true, "self": 28.5910124509453 }, "communicator.exchange": { "total": 1401.0511392170793, "count": 63964, "is_parallel": true, "self": 1401.0511392170793 }, "steps_from_proto": { "total": 116.39108115490558, "count": 63964, "is_parallel": true, "self": 24.43380236988196, "children": { "_process_rank_one_or_two_observation": { "total": 91.95727878502362, "count": 511712, "is_parallel": true, "self": 91.95727878502362 } } } } } } } } } } }, "trainer_advance": { "total": 683.2586813870187, "count": 63965, "self": 3.448115081010428, "children": { "process_trajectory": { "total": 141.15001765100624, "count": 63965, "self": 140.9046369450066, "children": { "RLTrainer._checkpoint": { "total": 0.24538070599965067, "count": 2, "self": 0.24538070599965067 } } }, "_update_policy": { "total": 538.660548655002, "count": 448, "self": 317.5441730760647, "children": { "TorchPPOOptimizer.update": { "total": 221.11637557893732, "count": 22824, "self": 221.11637557893732 } } } } } } }, "trainer_threads": { "total": 1.5910000001895241e-06, "count": 1, "self": 1.5910000001895241e-06 }, "TrainerController._save_models": { "total": 0.14181539400033216, "count": 1, "self": 0.0023631240001122933, "children": { "RLTrainer._checkpoint": { "total": 0.13945227000021987, "count": 1, "self": 0.13945227000021987 } } } } } } }